The Greenland–Iceland–Faroe Ridge,located between the central eastern part of Greenland and the northwestern edge of Europe,spans across the North Atlantic.As the core component of the Greenland–Iceland–Faroe Ridg...The Greenland–Iceland–Faroe Ridge,located between the central eastern part of Greenland and the northwestern edge of Europe,spans across the North Atlantic.As the core component of the Greenland–Iceland–Faroe Ridge,the Iceland is an alkaline basalt area,which belongs to the periodic submarine magmatism and submarine volcano eruption resulting from mantle plume upwelling(Jiang et al.,2020).For the oceanic plateaus,the characteristics of the Iceland are closest to the continental crust,so the Iceland is considered the most suitable for simulating the earliest continental crust on the Earth(Reimink et al.,2014).展开更多
Metamorphic basement is widespread in northeastern Jiangxi Province withcomplicated geological structure and enriched polymetallic deposits. It is one of the impor-tant areas for geological research in China, especial...Metamorphic basement is widespread in northeastern Jiangxi Province withcomplicated geological structure and enriched polymetallic deposits. It is one of the impor-tant areas for geological research in China, especially for study of deep fault belt展开更多
Extracting features from original signals is a key procedure for traditional fault diagnosis of induction motors, as it directly influences the performance of fault recognition. However, high quality features need exp...Extracting features from original signals is a key procedure for traditional fault diagnosis of induction motors, as it directly influences the performance of fault recognition. However, high quality features need expert knowledge and human intervention. In this paper, a deep learning approach based on deep belief networks （DBN） is developed to learn features from frequency distribution of vibration signals with the purpose of characterizing work- ing status of induction motors. It combines feature extraction procedure with classification task together to achieve automated and intelligent fault diagnosis. The DBN model is built by stacking multiple-units of restricted Boltzmann machine （RBM）, and is trained using layer-by- layer pre-training algorithm. Compared with traditional diagnostic approaches where feature extraction is needed, the presented approach has the ability of learning hierar- chical representations, which are suitable for fault classi- fication, directly from frequency distribution of the measurement data. The structure of the DBN model is investigated as the scale and depth of the DBN architecture directly affect its classification performance. Experimental study conducted on a machine fault simulator verifies the effectiveness of the deep learning approach for fault diagnosis of induction motors. This research proposes an intelligent diagnosis method for induction motor which utilizes deep learning model to automatically learn features from sensor data and realize working status recognition.展开更多
Aiming at evaluating the stability of a rock mass near a fault,a microseismic(MS) monitoring system was established in Hongtoushan copper mine.The distribution of displacement and log(/),the relationship between MS ac...Aiming at evaluating the stability of a rock mass near a fault,a microseismic(MS) monitoring system was established in Hongtoushan copper mine.The distribution of displacement and log(/),the relationship between MS activity and the exploitation process,and the stability of the rock mass controlled by a fault were studied.The results obtained from microseismic data showed that MS events were mainly concentrated al the footwall of the fault.When the distance to the fault exceeded 20 m,the rock mass reached a relatively stable state.MS activity is closely related to the mining process.Under the strong disturbance from blasting,the initiation and propagation of cracks is much faster.MS activity belongs in the category of aftershocks after large scale excavation.The displacement and log(C/) obtained from MS events can reflect the difference in physical and mechanical behavior of different areas within the rock mass,which is useful in judging the integrity and degradation of the rock mass.展开更多
Altun fault is regarded as a large\|scale sinistral strike\|slip fault, it is composed of several faults with the different character, and there is a special geological structure in the fault belt, and they constitute...Altun fault is regarded as a large\|scale sinistral strike\|slip fault, it is composed of several faults with the different character, and there is a special geological structure in the fault belt, and they constitute the northwestern margin fault belt of the Qinghai\|Tibetan plateau. In order to investigate the deep crust structure in the Altun region, layers which Tarim lithosphere subducted beneath the Qinghai\|Tibetan plateau, the forward structure of the subduction plate and the scale of the plate subduction, a deep seismic reflection profile was designed. Data collection work of the deep seismic reflection profile across Altun fault was completed during 24/8/1999 to 25/9/1999. The profile locates in Qiemo county, Xinjiang Uygur Autonomous Region, the southern end of the profile stretches into Altun Mountains, the northern end locates in the Tarim desert margin. The profile is nearly SN trending and crosses the main Altun fault. The profile totally is 145km long, time record is 30 seconds, the smallest explosive amount is 72～100kg, the biggest explosive amount reaches 200～300kg, the explosive distance is 800m, and detectors are laid at a 50m distance.展开更多
A study of faults and their control of deep gas accumulations has been made on the basis of dividing fault systems in the Xujiaweizi area. The study indicates two sets of fault systems are developed vertically in the ...A study of faults and their control of deep gas accumulations has been made on the basis of dividing fault systems in the Xujiaweizi area. The study indicates two sets of fault systems are developed vertically in the Xujiaweizi area, including a lower fault system and an upper fault system. Formed in the period of the Huoshiling Formation to Yingcheng Formation, the lower fault system consists of five fault systems including Xuxi strike-slip extensional fault system, NE-trending extensional fault system, near-EW-trending regulating fault system, Xuzhong strike-slip fault system and Xudong strike-slip fault system. Formed in the period of Qingshankou Formation to Yaojia Formation, the upper fault system was affected mainly by the boundary conditions of the lower fault system, and thus plenty of muiti-directionally distributed dense fault zones were formed in the T2 reflection horizon. The Xuxi fault controlled the formation and distribution of Shahezi coal-measure source rocks, and Xuzhong and Xndong faults controlled the formation and distribution of volcanic reservoirs of Y1 Member and Y3 Member, respectively. In the forming period of the upper fault system, the Xuzhong fault was of successive strong activities and directly connected gas source rock reservoirs and volcanic reservoirs, so it is a strongly-charged direct gas source fault. The volcanic reservoir development zones of good physical properties that may be found near the Xuzhong fault are the favorable target zones for the next exploration of deep gas accumulations in Xujiaweizi area.展开更多
The Erlian fault basin group, a typical Basin and Range type fault basin group, was formed during Late Jurassic to Early Cretaceous, in which there are rich coal, oil and gas resources. In the present paper the abund...The Erlian fault basin group, a typical Basin and Range type fault basin group, was formed during Late Jurassic to Early Cretaceous, in which there are rich coal, oil and gas resources. In the present paper the abundant geological and petroleum information accumulated in process of industry oil and gas exploration and development of the Erlian basin group is comprehensively analyzed, the structures related to formation of basin are systematically studied, and the complete extensional tectonic system of this basin under conditions of wide rift setting and low extensional ratio is revealed by contrasting study with Basin and Range Province of the western America. Based on the above studies and achievements of the former workers, the deep background of the basin development is treated.展开更多
Since the effectiveness of extracting fault features is not high under traditional bearing fault diagnosis method, a bearing fault diagnosis method based on Deep Auto-encoder Network (DAEN) optimized by Cloud Adaptive...Since the effectiveness of extracting fault features is not high under traditional bearing fault diagnosis method, a bearing fault diagnosis method based on Deep Auto-encoder Network (DAEN) optimized by Cloud Adaptive Particle Swarm Optimization (CAPSO) was proposed. On the basis of analyzing CAPSO and DAEN, the CAPSO-DAEN fault diagnosis model is built. The model uses the randomness and stability of CAPSO algorithm to optimize the connection weight of DAEN, to reduce the constraints on the weights and extract fault features adaptively. Finally, efficient and accurate fault diagnosis can be implemented with the Softmax classifier. The results of test show that the proposed method has higher diagnostic accuracy and more stable diagnosis results than those based on the DAEN, Support Vector Machine (SVM) and the Back Propagation algorithm (BP) under appropriate parameters.展开更多
Based on the results of surface geology, shallow and deep seismic survey, features of micro-earthquake activity along the north boundary fault of Yanqing-Fanshan sub-basin and their relationship with the surface activ...Based on the results of surface geology, shallow and deep seismic survey, features of micro-earthquake activity along the north boundary fault of Yanqing-Fanshan sub-basin and their relationship with the surface active faults and the deep-seated crustal structure are analyzed using the recordings from the high-resolution digital seismic network. The focal mechanism solutions of micro-earthquakes, whose locations are precisely determined by the seismic network, have confirmed the structural characteristics to be the rotational planar normal fault and demon-strated the surface traces of the north boundary fault of Yanqing-Fanshan sub-basin. By using the digital recordings of earthquakes with the high resolutions and analyzing the mechanism solutions, our study has revealed the rela-tionship between the geological phenomena in the shallow and deep structures in Yanqing-Huailai basin and the transition features from the brittle to ductile deformation with the crustal depth.展开更多
A comprehensive discussion on the deep seated genesis of gold metallogenic materials and the tectono magmatic controls over gold deposits is given in this paper, which is based on the crustal and upper mantle struct...A comprehensive discussion on the deep seated genesis of gold metallogenic materials and the tectono magmatic controls over gold deposits is given in this paper, which is based on the crustal and upper mantle structural characteristics of the Jiaodong massif, the property, activation history and styles of the Tancheng Lujiang fault zone, as well as a series of accompanying tectono magmatic events. Prediction for further prospecting gold deposits in the area is also made.展开更多
In the cloud computing, in order to provide reliable and continuous service, the need for accurate and timely fault detection is necessary. However, cloud failure data, especially cloud fault feature data acquisition ...In the cloud computing, in order to provide reliable and continuous service, the need for accurate and timely fault detection is necessary. However, cloud failure data, especially cloud fault feature data acquisition is difficult and the amount of data is too small, with large data training methods to solve a certain degree of difficulty. Therefore, a fault detection method based on depth learning is proposed. An auto-encoder with sparse denoising is used to construct a parallel structure network. It can automatically learn and extract the fault data characteristics and realize fault detection through deep learning. The experiment shows that this method can detect the cloud computing abnormality and determine the fault more effectively and accurately than the traditional method in the case of the small amount of cloud fault feature data.展开更多
This paper examines the progression and advancements in fault detection techniques for photovoltaic (PV) panels, a target for optimizing the efficiency and longevity of solar energy systems. As the adoption of PV tech...This paper examines the progression and advancements in fault detection techniques for photovoltaic (PV) panels, a target for optimizing the efficiency and longevity of solar energy systems. As the adoption of PV technology grows, the need for effective fault detection strategies becomes increasingly paramount to maximize energy output and minimize operational downtimes of solar power systems. These approaches include the use of machine learning and deep learning methodologies to be able to detect the identified faults in PV technology. Here, we delve into how machine learning models, specifically kernel-based extreme learning machines and support vector machines, trained on current-voltage characteristic (I-V curve) data, provide information on fault identification. We explore deep learning approaches by taking models like EfficientNet-B0, which looks at infrared images of solar panels to detect subtle defects not visible to the human eye. We highlight the utilization of advanced image processing techniques and algorithms to exploit aerial imagery data, from Unmanned Aerial Vehicles (UAVs), for inspecting large solar installations. Some other techniques like DeepLabV3 , Feature Pyramid Networks (FPN), and U-Net will be detailed as such tools enable effective segmentation and anomaly detection in aerial panel images. Finally, we discuss implications of these technologies on labor costs, fault detection precision, and sustainability of PV installations.展开更多
基金granted by National Natural Science Foundation of China(Grant No.42172224)。
文摘The Greenland–Iceland–Faroe Ridge,located between the central eastern part of Greenland and the northwestern edge of Europe,spans across the North Atlantic.As the core component of the Greenland–Iceland–Faroe Ridge,the Iceland is an alkaline basalt area,which belongs to the periodic submarine magmatism and submarine volcano eruption resulting from mantle plume upwelling(Jiang et al.,2020).For the oceanic plateaus,the characteristics of the Iceland are closest to the continental crust,so the Iceland is considered the most suitable for simulating the earliest continental crust on the Earth(Reimink et al.,2014).
文摘Metamorphic basement is widespread in northeastern Jiangxi Province withcomplicated geological structure and enriched polymetallic deposits. It is one of the impor-tant areas for geological research in China, especially for study of deep fault belt
基金Supported by National Natural Science Foundation of China(Grant No.51575102)Fundamental Research Funds for the Central Universities of ChinaJiangsu Provincial Research Innovation Program for College Graduates of China(Grant No.KYLX16_0191)
文摘Extracting features from original signals is a key procedure for traditional fault diagnosis of induction motors, as it directly influences the performance of fault recognition. However, high quality features need expert knowledge and human intervention. In this paper, a deep learning approach based on deep belief networks （DBN） is developed to learn features from frequency distribution of vibration signals with the purpose of characterizing work- ing status of induction motors. It combines feature extraction procedure with classification task together to achieve automated and intelligent fault diagnosis. The DBN model is built by stacking multiple-units of restricted Boltzmann machine （RBM）, and is trained using layer-by- layer pre-training algorithm. Compared with traditional diagnostic approaches where feature extraction is needed, the presented approach has the ability of learning hierar- chical representations, which are suitable for fault classi- fication, directly from frequency distribution of the measurement data. The structure of the DBN model is investigated as the scale and depth of the DBN architecture directly affect its classification performance. Experimental study conducted on a machine fault simulator verifies the effectiveness of the deep learning approach for fault diagnosis of induction motors. This research proposes an intelligent diagnosis method for induction motor which utilizes deep learning model to automatically learn features from sensor data and realize working status recognition.
基金financially supported by Projects of the National Key Technology R&D Program of China(Nos.2013BAB02B01 and2013BAB02B03)the National Natural Science Foundation of China(Nos.51274055 and 51204030)+1 种基金the Fundamental Research Funds for the Central University of China(Nos.N130401006,N120801002 and N120701001)the Key Science&Technology Special Project of Third Five-Year Plan of MCC(No.0012012009)
文摘Aiming at evaluating the stability of a rock mass near a fault,a microseismic(MS) monitoring system was established in Hongtoushan copper mine.The distribution of displacement and log(/),the relationship between MS activity and the exploitation process,and the stability of the rock mass controlled by a fault were studied.The results obtained from microseismic data showed that MS events were mainly concentrated al the footwall of the fault.When the distance to the fault exceeded 20 m,the rock mass reached a relatively stable state.MS activity is closely related to the mining process.Under the strong disturbance from blasting,the initiation and propagation of cracks is much faster.MS activity belongs in the category of aftershocks after large scale excavation.The displacement and log(C/) obtained from MS events can reflect the difference in physical and mechanical behavior of different areas within the rock mass,which is useful in judging the integrity and degradation of the rock mass.
文摘Altun fault is regarded as a large\|scale sinistral strike\|slip fault, it is composed of several faults with the different character, and there is a special geological structure in the fault belt, and they constitute the northwestern margin fault belt of the Qinghai\|Tibetan plateau. In order to investigate the deep crust structure in the Altun region, layers which Tarim lithosphere subducted beneath the Qinghai\|Tibetan plateau, the forward structure of the subduction plate and the scale of the plate subduction, a deep seismic reflection profile was designed. Data collection work of the deep seismic reflection profile across Altun fault was completed during 24/8/1999 to 25/9/1999. The profile locates in Qiemo county, Xinjiang Uygur Autonomous Region, the southern end of the profile stretches into Altun Mountains, the northern end locates in the Tarim desert margin. The profile is nearly SN trending and crosses the main Altun fault. The profile totally is 145km long, time record is 30 seconds, the smallest explosive amount is 72～100kg, the biggest explosive amount reaches 200～300kg, the explosive distance is 800m, and detectors are laid at a 50m distance.
基金supported by the National Natural Foundation Project Polygonal Fault Genetic Mechanism and its Reservoir Controlling Mechanism in Rift Basin (number: 41072163) financial aid
文摘A study of faults and their control of deep gas accumulations has been made on the basis of dividing fault systems in the Xujiaweizi area. The study indicates two sets of fault systems are developed vertically in the Xujiaweizi area, including a lower fault system and an upper fault system. Formed in the period of the Huoshiling Formation to Yingcheng Formation, the lower fault system consists of five fault systems including Xuxi strike-slip extensional fault system, NE-trending extensional fault system, near-EW-trending regulating fault system, Xuzhong strike-slip fault system and Xudong strike-slip fault system. Formed in the period of Qingshankou Formation to Yaojia Formation, the upper fault system was affected mainly by the boundary conditions of the lower fault system, and thus plenty of muiti-directionally distributed dense fault zones were formed in the T2 reflection horizon. The Xuxi fault controlled the formation and distribution of Shahezi coal-measure source rocks, and Xuzhong and Xndong faults controlled the formation and distribution of volcanic reservoirs of Y1 Member and Y3 Member, respectively. In the forming period of the upper fault system, the Xuzhong fault was of successive strong activities and directly connected gas source rock reservoirs and volcanic reservoirs, so it is a strongly-charged direct gas source fault. The volcanic reservoir development zones of good physical properties that may be found near the Xuzhong fault are the favorable target zones for the next exploration of deep gas accumulations in Xujiaweizi area.
文摘The Erlian fault basin group, a typical Basin and Range type fault basin group, was formed during Late Jurassic to Early Cretaceous, in which there are rich coal, oil and gas resources. In the present paper the abundant geological and petroleum information accumulated in process of industry oil and gas exploration and development of the Erlian basin group is comprehensively analyzed, the structures related to formation of basin are systematically studied, and the complete extensional tectonic system of this basin under conditions of wide rift setting and low extensional ratio is revealed by contrasting study with Basin and Range Province of the western America. Based on the above studies and achievements of the former workers, the deep background of the basin development is treated.
文摘Since the effectiveness of extracting fault features is not high under traditional bearing fault diagnosis method, a bearing fault diagnosis method based on Deep Auto-encoder Network (DAEN) optimized by Cloud Adaptive Particle Swarm Optimization (CAPSO) was proposed. On the basis of analyzing CAPSO and DAEN, the CAPSO-DAEN fault diagnosis model is built. The model uses the randomness and stability of CAPSO algorithm to optimize the connection weight of DAEN, to reduce the constraints on the weights and extract fault features adaptively. Finally, efficient and accurate fault diagnosis can be implemented with the Softmax classifier. The results of test show that the proposed method has higher diagnostic accuracy and more stable diagnosis results than those based on the DAEN, Support Vector Machine (SVM) and the Back Propagation algorithm (BP) under appropriate parameters.
文摘Based on the results of surface geology, shallow and deep seismic survey, features of micro-earthquake activity along the north boundary fault of Yanqing-Fanshan sub-basin and their relationship with the surface active faults and the deep-seated crustal structure are analyzed using the recordings from the high-resolution digital seismic network. The focal mechanism solutions of micro-earthquakes, whose locations are precisely determined by the seismic network, have confirmed the structural characteristics to be the rotational planar normal fault and demon-strated the surface traces of the north boundary fault of Yanqing-Fanshan sub-basin. By using the digital recordings of earthquakes with the high resolutions and analyzing the mechanism solutions, our study has revealed the rela-tionship between the geological phenomena in the shallow and deep structures in Yanqing-Huailai basin and the transition features from the brittle to ductile deformation with the crustal depth.
文摘A comprehensive discussion on the deep seated genesis of gold metallogenic materials and the tectono magmatic controls over gold deposits is given in this paper, which is based on the crustal and upper mantle structural characteristics of the Jiaodong massif, the property, activation history and styles of the Tancheng Lujiang fault zone, as well as a series of accompanying tectono magmatic events. Prediction for further prospecting gold deposits in the area is also made.
文摘In the cloud computing, in order to provide reliable and continuous service, the need for accurate and timely fault detection is necessary. However, cloud failure data, especially cloud fault feature data acquisition is difficult and the amount of data is too small, with large data training methods to solve a certain degree of difficulty. Therefore, a fault detection method based on depth learning is proposed. An auto-encoder with sparse denoising is used to construct a parallel structure network. It can automatically learn and extract the fault data characteristics and realize fault detection through deep learning. The experiment shows that this method can detect the cloud computing abnormality and determine the fault more effectively and accurately than the traditional method in the case of the small amount of cloud fault feature data.
文摘This paper examines the progression and advancements in fault detection techniques for photovoltaic (PV) panels, a target for optimizing the efficiency and longevity of solar energy systems. As the adoption of PV technology grows, the need for effective fault detection strategies becomes increasingly paramount to maximize energy output and minimize operational downtimes of solar power systems. These approaches include the use of machine learning and deep learning methodologies to be able to detect the identified faults in PV technology. Here, we delve into how machine learning models, specifically kernel-based extreme learning machines and support vector machines, trained on current-voltage characteristic (I-V curve) data, provide information on fault identification. We explore deep learning approaches by taking models like EfficientNet-B0, which looks at infrared images of solar panels to detect subtle defects not visible to the human eye. We highlight the utilization of advanced image processing techniques and algorithms to exploit aerial imagery data, from Unmanned Aerial Vehicles (UAVs), for inspecting large solar installations. Some other techniques like DeepLabV3 , Feature Pyramid Networks (FPN), and U-Net will be detailed as such tools enable effective segmentation and anomaly detection in aerial panel images. Finally, we discuss implications of these technologies on labor costs, fault detection precision, and sustainability of PV installations.
